Enables MCP servers with the claude/channel capability to push permission decisions and requests via notifications, allowing server-side permission management.
Feature-flagged by tengu_harbor_permissions (default false). Additionally requires Teams/Enterprise opt-in.
- Uses
notifications/claude/channel/permissionandnotifications/claude/channel/permission_requestnotification paths - MCP servers must declare both
claude/channelandclaude/channel/permissionin capabilities - Teams/Enterprise opt-in: "Teams/Enterprise opt-in for channel notifications... Default off. Set true to allow; users then select servers via --channels."
- Includes an FNV-1a hash-based identifier system with profanity filtering for generated codes
Channel permissions infrastructure (gated by tengu_harbor_permissions, search for "notifications/claude/channel/permission")
Strings lifted out of the shipped bundle, so the claim above can be checked against them.
tengu_harbor_permissions On for this account, and not off by defaultThe flag server returned on for the one account this site reads, and nothing in this release compiles it off by default. The compiled default is shown below, and says which it is when we cannot read one: a fifth of gates compile in a string or a number rather than on or off, and most published releases have no gate table behind them at all. No client can see what the server returns for your account.
This account: on · anonymous baseline: on · compiled default in v2.1.81: no gate table built for this version
These values were read against a different version of Claude Code, so treat them as the nearest reading available instead of one taken on this release.
Read once, for one account on one subscription tier, against v2.1.81. It isn't a statement about your account. What a flag value here can and cannot tell you
A reading is one sample. Claude Code evaluates its flags remotely, so no client sees the targeting rule behind a value and this says nothing about your account.
A reading is one sample. Claude Code evaluates its flags remotely, so no client sees the targeting rule behind a value and this says nothing about your account.